# Pruve Pruve lê o histórico de um repositório para explicar por que determinadas linhas de código são como são, com evidências que podem ser abertas. Oferece contexto somente de leitura de repositórios do GitHub ou GitLab para desenvolvedores, gerentes de produto e agentes de IA. - Findings24: - Site: - Preços: Freemium - Categorias: Assistente de Código IA, Ferramentas Dev IA, Gerador de documentação com IA ## O que é Pruve? Pruve is a read-only product for exploring why code exists the way it does. It reads a repository’s history and ties individual lines back to the change that introduced them, so you can open the supporting discussion, commit, review thread, or agent session instead of relying on guesswork. The product is built around evidence. When a line can be explained, Pruve shows the receipts behind it; when it cannot, it says so plainly. That makes it useful for understanding unusual constants, merge decisions, undocumented behavior, and other code that is hard to interpret from the source alone. ## O que Pruve pode fazer? ### Line-level explanations with receipts Pruve answers questions about specific lines by tracing them back to the changes and discussions that wrote them. The result is a clickable chain of evidence rather than a speculative summary. ### Coverage visibility across a repository It classifies changes as explained, described, or undocumented, then surfaces that coverage in dashboards, file trees, and the code gutter so readers can see which parts of a codebase have recorded reasoning. ### Historical context from multiple source types Indexing can pull from commit messages, pull request bodies, review comments, linked issues, and agent sessions, which lets the product preserve the discussion around a change, not just the diff. ### Read-only browsing and questioning Pruve reads repository history and file contents without writing back to the code host. The only optional write action mentioned is a PR check run for the documentation gate. ### Agent access over MCP The product exposes read-only MCP tools so agents can inspect reasoning before editing code. This is meant to let automated workflows ask “why” before making a change. ### Coverage-based documentation gate Teams can optionally fail pull requests that have no recorded reasoning anywhere, turning missing context into an explicit review signal. ## Casos de uso ### Understanding strange or opaque code A developer can click a line, see the change that introduced it, and read the discussion that explains why it was added instead of reverse-engineering the intent from the implementation. ### Reviewing merge decisions and technical tradeoffs When a merge commit drops discussion context, Pruve can surface the issue, benchmark, review comment, or agent session that explains why a choice was made. ### Checking documentation coverage in a repository Teams can scan a codebase to see which files or folders have recorded reasoning and which areas are still undocumented, making gaps visible before they become maintenance problems. ### Giving agents safer read access An AI agent can use MCP tools to inspect receipts before editing code, helping it avoid changes based on invented rationale. ### Adding a repository-level reasoning gate Teams that want explicit evidence for pull requests can use the documentation gate to flag changes that lack recorded reasoning. ## Perguntas frequentes ### Does Pruve write to my repository? No. The product is read-only. The documentation says it does not push code, comments, or branches. The only write-related action mentioned is an optional PR check run for the documentation gate. ### What kinds of sources does Pruve read? It indexes repository history and related discussion, including commits, pull requests, review threads, issues, and agent sessions when they are available. ### What happens when Pruve cannot find a reason for a line? It says so rather than guessing. The product is designed to report what it searched and stop if there is no evidence. ### How is coverage defined? Coverage is counted as explained, described, or undocumented changes. Those counts are used in the product’s dashboards and line gutters. ### Is open source free? Yes. The pricing page says open source is free forever, with free and unmetered read-only access for receipts. ## Informações rápidas - **Category**: Developer Tool - **Primary use**: Explain why repository code exists the way it does - **Data source**: GitHub and GitLab repository history - **Access model**: Read-only browsing and questioning - **Agent support**: MCP tools for AI agents - **Pricing model**: Paid organisation plan for private repositories; free forever for open source